search

X-PLUG / mPLUG-2

mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video (ICML 2023)
Apache License 2.0
213 stars 17 forks source link

how to get train, valid, test #10

Open minuenergy opened 1 year ago

minuenergy commented 1 year ago

train_file: 'datasets/annotations_all/msrvtt_caption/train.jsonl' test_file: 'datasets/annotations_all/msrvtt_caption/test.jsonl' video_root: "datasets/MSRVTT/data/MSRVTT/videos/all"

i get YouTubeClips, AllVideoDescriptions.txt at https://www.cs.utexas.edu/users/ml/clamp/videoDescription/ (Videos, annotation) and get splits from https://github.com/albanie/collaborative-experts/blob/master/misc/datasets/msvd/README.md

ChdDongyang commented 11 months ago

Same problem, please tell me where can get these files.

malaka1109 commented 8 months ago

I have a question about the annotation file which localed in ./datasets/annotations_all/msrvtt_caption/train.jsonl, in video_downstream_datasets.py it need a key name's "golden_captions" which is not exist in my jsonl file. Am i get the wrong annotation file?

hely201314 commented 7 months ago

please tell me where can get these files.

godatta commented 6 months ago

Can you please tell me where to get these files?